Geekbench ML Score

547
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 13 2024 09:13 AM
Views 1

System Information

System Information
Operating System Android 11
Model Sony Xperia 1
Model IDSony J9110
Motherboard msmnile
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 5.36 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 650
69.7 IPS
 
Image Classification (F16)
100% 815
87.3 IPS
 
Image Classification (I8)
80% 1843
197.5 IPS
 
Image Segmentation (F32)
100% 724
4.47 IPS
 
Image Segmentation (F16)
100% 839
5.18 IPS
 
Image Segmentation (I8)
89% 4947
30.6 IPS
 
Pose Estimation (F32)
100% 356
1.44 IPS
 
Pose Estimation (F16)
100% 833
3.37 IPS
 
Pose Estimation (I8)
80% 3248
13.1 IPS
 
Object Detection (F32)
100% 275
9.63 IPS
 
Object Detection (F16)
100% 377
13.2 IPS
 
Object Detection (I8)
52% 654
23.0 IPS
 
Face Detection (F32)
100% 997
11.4 IPS
 
Face Detection (F16)
97% 1038
11.9 IPS
 
Face Detection (I8)
75% 3197
36.7 IPS
 
Text Classification (F32)
54% 14
5.50 IPS
 
Text Classification (F16)
54% 13
5.25 IPS
 
Machine Translation (F32)
100% 305
47.0 IPS
 
Machine Translation (F16)
100% 305
47.0 IPS
 

Compare

Set Baseline Geekbench 6 now available